Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/dropfan/claude-code-plugins/lark-appsnpx skills add DropFan/claude-code-plugins --skill lark-appsgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00331 | $0.05586 |
| Opus 5 | $0.00166 | $0.02793 |
| Sonnet 5 | $0.00066 | $0.01117 |
| Haiku 4.5 | $0.00033 | $0.00559 |
Grade A, and why
lark-apps scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
97% identical to lark-apps — 60 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚙️ Cowork / Claude Desktop 执行环境说明（自动注入）
本技能依赖本地
lark-cli（@larksuite/cli，可用command -v lark-cli定位）及其~/.lark-cli登录态（应用密钥存于 macOS keychain）。在 Cowork 中运行任何
lark-cli命令时，必须在本地 macOS 上执行（使用 Desktop Commander 的start_process/interact_with_process，或其它本地 shell 工具），不要用隔离的 Linux 沙箱mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。 执行前确保 npm 全局 bin 目录（npm prefix -g输出目录下的bin）在 PATH 中。（在 Claude Code 中可忽略本说明，lark-cli 在本机 shell 直接可用。）
apps (v1)
妙搭应用属于用户资产。默认用 --as user；认证、scope、exit-10、高风险确认、_notice 等通用处理只读 ../lark-shared/SKILL.md，不要在本 skill 里复制。妙搭应用有两条开发路径：本地开发（拉源码本地写）/ 云端会话（妙搭 AI 生成）。
身份与授权
妙搭应用是用户的个人资产，统一 --as user（见开头）。已有用户身份可用时直接执行业务命令，不要为了预防权限问题主动重新登录，否则可能中断原任务并触发不必要的设备授权。仅当 CLI 明确返回未登录或缺少本域 scope 时，一次性执行：
lark-cli auth login --domain apps
因缺权限失败（error.subtype == "missing_scope"）时的通用处理见 ../lark-shared/SKILL.md，同样按 --domain apps 授权；授权成功后只恢复原业务操作，不扩展任务范围。
意图路由
按具体操作查命令（开发路径先用下方「选择开发路径」判定表定好再进来取命令）：
| 用户意图 | 先用 | 按需读取 |
|---|---|---|
| 创建新应用资产、拿 app_id | +create |
lark-apps-create.md |
| 找已有 app_id、按名字过滤应用 | +list --keyword <name> |
lark-apps-list.md |
| 查单个应用详情（类型、名称、发布状态等） | +get --app-id <app_id> |
lark-apps-get.md |
| 改应用名或描述 | +update |
lark-apps-update.md |
| HTML 应用 / 创意模式 — 写 HTML 页面/网站、静态页、PPT/deck、落地页、仪表盘、UI mockup、原型、线框图、视觉探索 | 加载 creative-design/creative-design.md（含完整开发与发布流程） |
creative-design/creative-design.md |
| 旧版存量 HTML 应用（无 Git 管理）继续上传已有静态产物 | +html-publish（仅兼容旧链路；新建 html / 创意模式 / creative-design 产物不得使用） |
lark-apps-html-publish.md |
开发已有应用 / 初始化本地仓库（开发方式已定为本地后；先解析 app_id，勿 +create 新建） |
+init（或手动 +git-credential-init + 原生 git）。执行前必读 lark-apps-local-dev.md，含端到端流程和领域规则 |
lark-apps-init.md, lark-apps-git-credential.md |
本地开发时 .env.local 损坏/丢失，重新拉取启动期环境变量 |
+env-pull |
lark-apps-env-pull.md |
| 管理应用环境变量（查看/设置/删除） | +env-list, +env-set, +env-delete |
lark-apps-env.md |
| 查线上日志、Trace、请求数、错误率、延迟、CPU、memory、PV/UV/访问量 | +log-list, +log-get, +trace-list, +trace-get, +metric-list, +analytics-list |
lark-apps-observability.md |
| 看表 / 看结构 / 初始化多环境 / 导入导出数据 / 变更追溯 / 行级审计 / dev→online 发布 / 时间点恢复 / 查 DB 用量 | +db-table-list、+db-table-get、+db-env-create、+db-data-export/+db-data-import、+db-changelog-list、+db-audit-status/+db-audit-enable/+db-audit-disable/+db-audit-list、+db-env-diff/+db-env-migrate、+db-recovery-diff/+db-recovery-apply、+db-quota-get |
lark-apps-db.md |
| 逐条执行 SQL（SELECT / DML / DDL）；建表 / 改表 / 写 SQL 的平台规范 | +db-execute |
lark-apps-db-execute.md（含「平台 SQL 规范」：审计列 / RLS / user_profile / 禁用 SQL / PG 陷阱） |
| 管理应用文件存储：上传/下载本地文件、列出/查看/删除已存文件、生成临时分享链接、查存储用量 | +file-upload/+file-download/+file-list/+file-get/+file-sign/+file-delete/+file-quota-get |
lark-apps-file.md |
| 调试应用运行时缓存：查看/删除单个业务 key、清空指定环境缓存 | +cache-get/+cache-delete/+cache-clear |
lark-apps-cache.md |
| 部署/上线应用（"部署""上线""推上去并部署""发布到云端"）；查发布状态/历史 | 本地开发链路先按 lark-apps-local-dev.md 确认本次改动已 git commit + git push，再用 +release-create / +release-get；查历史用 +release-list |
lark-apps-local-dev.md, lark-apps-release-create.md, lark-apps-release-get.md, lark-apps-release-list.md |
| 设置或查看运行时可见范围 | +access-scope-set, +access-scope-get |
对应 access-scope reference |
| 创意模式（html）应用的评论相关操作 | 创意模式应用评论走 lark-drive 文档评论体系，读取 ../lark-drive/SKILL.md 了解评论能力 |
../lark-drive/SKILL.md |
管理 app_... 应用内角色、角色成员，或查询用户匹配角色 |
+role-list/get/create/update/delete, +role-member-list/add/remove, +role-match-list |
lark-apps-role.md |
| 云端 Agent 生成/迭代应用（开发方式已定为云端后） | +session-create -> +chat -> +session-get |
lark-apps-cloud-dev.md |
| 管理妙搭应用开放 API Key（创建/查看/启停/重置/删除凭证；密钥仅 create/reset 一次性返回） | +openapi-key-list/get/create/update/enable/disable/delete/reset |
lark-apps-openapi-key.md |
| 管理妙搭应用自动化触发器（定时/记录变更/Webhook/飞书审批四类触发器的查询/创建/更新/启停；Webhook URL·Token 一次性回显、不落盘） | +automation-list/get/create/update/enable/disable |
lark-apps-automation.md |
| 查看某次会话某一轮（turn）的回复消息（含仍在生成中的本轮）/ 导出上一轮模型回复（"这一轮回复了什么""上一轮的回复""导出某轮消息"） | 先 +session-get（取 latest_turn.turn_id）-> +session-messages-list --turn-id <id>（仅 user 身份；分页用 --page-token） |
lark-apps-session-messages-list.md |
| 外部能力(AI模型能力和飞书平台能力)集成/插件/Plugin/Capability | +plugin-install, +plugin-list, +plugin-uninstall |
lark-apps-plugin-install.md, lark-apps-plugin-uninstall.md, lark-apps-plugin-list.md |
What ships with it
53 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- creative-design/agents/assets/vision-probe.png 263 B
- creative-design/agents/fork-verifier-agent.md 3.9 KB
- creative-design/agents/vision-probe-agent.md 1.3 KB
- creative-design/assets/index.html 829 B
- creative-design/creative-design.md 32 KB
- creative-design/references/aily.md 4.2 KB
- creative-design/references/animated-video.md 5.4 KB
- creative-design/references/charts.md 9.4 KB
- creative-design/references/claude.md 3.2 KB
- creative-design/references/codex.md 2.8 KB
- creative-design/references/data-report.md 8.5 KB
- creative-design/references/frontend-design.md 9.0 KB
- creative-design/references/hi-fi-design.md 2.8 KB
- creative-design/references/interactive-prototype.md 2.2 KB
- creative-design/references/make-a-deck.md 16 KB
- creative-design/references/visual-exposure.md 8.3 KB
- creative-design/references/wireframe.md 1.3 KB
- creative-design/starter-components/android-frame.jsx 8.1 KB
- creative-design/starter-components/animations.jsx 25 KB
- creative-design/starter-components/browser-window.jsx 4.2 KB
- creative-design/starter-components/deck-stage.js 113 KB runs code
- creative-design/starter-components/design-canvas.jsx 77 KB
- creative-design/starter-components/ios-frame.jsx 12 KB
- creative-design/starter-components/macos-window.jsx 8.2 KB
- creative-design/starter-components/tweaks-panel.jsx 35 KB
- references/lark-apps-access-scope-get.md 1.1 KB
- references/lark-apps-access-scope-set.md 2.0 KB
- references/lark-apps-automation.md 25 KB
- references/lark-apps-cache.md 4.5 KB
- references/lark-apps-cloud-dev.md 8.5 KB
- references/lark-apps-create.md 1.6 KB
- references/lark-apps-db-execute.md 14 KB
- references/lark-apps-db.md 13 KB
- references/lark-apps-env-pull.md 1.8 KB
- references/lark-apps-env.md 2.8 KB
- references/lark-apps-file.md 5.7 KB
- references/lark-apps-get.md 1.6 KB
- references/lark-apps-git-credential.md 2.0 KB
- references/lark-apps-html-publish.md 3.6 KB
- references/lark-apps-init.md 2.2 KB
- references/lark-apps-list.md 2.0 KB
- references/lark-apps-local-dev.md 10 KB
- references/lark-apps-observability.md 3.7 KB
- references/lark-apps-openapi-key.md 4.5 KB
- references/lark-apps-plugin-install.md 1.4 KB
- references/lark-apps-plugin-list.md 733 B
- references/lark-apps-plugin-uninstall.md 719 B
- references/lark-apps-release-create.md 2.1 KB
- references/lark-apps-release-get.md 2.0 KB
- references/lark-apps-release-list.md 1.1 KB
- references/lark-apps-role.md 8.1 KB
- references/lark-apps-session-messages-list.md 3.1 KB
- references/lark-apps-update.md 1.0 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 134 lines · 331 tokens per session scan A 0ad438d2f3a8
lark-apps is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 331 tokens to every session and 5,586 once invoked, about $0.0017 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to lark-apps, differing in 60 lines, and is treated as a copy.
Other skills, from other repositories
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.
skill-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.